China's open AI models vulnerable to backdoor threats
A security company recently conducted an open artificial intelligence experiment revealing serious potential security flaws in China-built AI models in use around the world -- flaws that China could exploit for cyberattacks, cyberespionage and other nefarious online activities.
A security company’s experiment uncovered significant security flaws in AI models developed in China. These vulnerabilities could potentially be exploited by China for malicious online activities such as cyberattacks and espionage. The AI models in question are currently in use globally.
- An open AI experiment revealed potential security flaws in China-built AI models.
- These flaws could allow China to conduct cyberattacks and cyberespionage.
- The affected AI models are reportedly in use worldwide.
Write a comment